检索结果-内蒙古大学图书馆

A Study on Wheel Member Condition Recognition Using machine learning (Support Vector machine)

SENSORS 2023年第20期23卷 8455页

作者： Lee, Jin-Han Lee, Jun-Hee Yun, Kwang-Su Bae, Han Byeol Kim, Sun Young Jeong, Jae-Hoon Kim, Jin-Pyung Busan Transportat Corp Busan 47353 South Korea Kunsan Natl Univ Sch Software Engn Gunsan 54150 South Korea Kunsan Natl Univ Sch Mech Engn Gunsan 54150 South Korea Global Bridge Co Ltd Incheon 21990 South Korea

The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the z-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%.

关键词： recognizing condition algorithm machine learning algorithm wheel tire

来源：评论

学校读者我要写书评

暂无评论

Estimation of Varietal Classification and Quality Analysis in Rice Seeds Using Digital Image Processing - A Survey

Estimation of Varietal Classification and Quality Analysis i...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Sandhiya, M. Christy, S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (纸本)9798350305708

Agriculture plays a major role in today's world. 70% of rice production is cultivated in south India. Thailand, the US, India, Vietnam, etc., are exporting rice all over the world. But they are facing one of the most difficult tasks: assuring the rice seed quality. Good seeds can increase production, so selecting seeds is very important. A maximum of the work was done physically or by using huge, expensive machines. For choosing good seeds, agronomists be conscious of two factors, such as the variety which is determined by some quality criteria, and next by the skilled one who is going to analyze the rice seed physically. Both tasks take a long time and the result of accuracy is also not as expected. Nowadays computer vision technology with Digital Image Processing plays a major role in many fields, namely agronomy, healthcare, machine vision, pattern recognition, remote sensing, Video processing, etc. Our research work mainly focuses on the agricultural arena, going to provide good quality seeds and identify dissimilar varieties of rice seeds by digital image processing techniques such as image capturing, segmenting the rice seeds, extracting the features from the rice seeds and finally feeding into the machine learning algorithm to find out the accuracy too. © 2023 IEEE.

关键词： Classification of rice seeds machine learning algorithm machine vision Quality analysis of rice seed Rice seed varietal purity

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Power Metering Automation for Improving data Integrity and Reliability in Power Marketing Meters

IoT-Based Power Metering Automation for Improving data Integ...

引用

2023 International Conference on Evolutionary algorithms and Soft Computing Techniques, EASCT 2023

作者： Samreen, Sumaiya Chanti, Yerrolla Mounika, P. Mandava, Manjusha Kruthika, C.G. Malla Reddy Engineering College for Women It Department Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

The goal of this paper is to provide an internet of things (IoT)-based approach for automated electricity metering. When measuring power using standard methods, inaccuracies and erroneous readings are possible, putting the data's integrity and authenticity at risk. The suggested method employs sensors linked to the internet of things (IoT) and machine learning algorithms to detect abnormalities and inconsistencies in real-time energy use statistics. This was evident during the testing phase. The proposed method offers several benefits over the present standard of power metering systems in use. The testing findings demonstrated that the proposed system is more reliable and effective in terms of 0.957 success rate, 0.943 accuracy, 0.967 recall, 0.956 F1 score and 0.982 AUC. © 2023 IEEE.

关键词： Anomaly detection Cloud-based data storage and analysis platform Internet of Things (IoT) machine learning algorithm Power metering Real-time data analysis User interface

来源：评论

学校读者我要写书评

暂无评论

Identification of DTL as Related Biomarker and Immune Infiltration Characteristics of Nasopharyngeal Carcinoma via Comprehensive Strategies

引用

INTERNATIONAL JOURNAL OF GENERAL MEDICINE 2022年 15卷 2329-2345页

作者： Wang, Hehe Zhang, Junge Ningbo First Hosp Dept Otolaryngol Head & Neck Surg Ningbo 315010 Zhejiang Peoples R China Ningbo First Hosp Dept Anesthesiol Ningbo Zhejiang Peoples R China

Purpose: Although considerable progress has been made in basic and clinical research on nasopharyngeal carcinoma (NPC), the biomarkers of the progression of NPC have not been fully studied and described. This study was designed to identify potential novel biomarkers for NPC using integrated analyses and explore the immune cell infiltration in this pathological process. Methods: Five GEO data sets were downloaded from gene expression omnibus database (GEO) and analysed to identify differentially expressed genes (DEGs), followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. The four algorithms were adopted for screening of novel and key biomarkers for NPC, including random forest (RF) machine learning algorithm, least absolute shrinkage and selection operator (LASSO) logistic regression, support vector machinerecursive feature elimination (SVM-RFE), and weighted gene co-expression network analysis (WGCNA). Lastly, CIBERSORT was used to assess the infiltration of immune cells in NPC, and the correlation between diagnostic markers and infiltrating immune cells was analyzed. Results: Herein, we identified 46 DEGs, and enrichment analysis results showed that DEGs and several kinds of signaling pathways might be closely associated with the occurrence and progression of NPC. DTL was recognized as NPC-related biomarker. DTL, also known as retinoic acid-regulated nuclear matrix-associated protein (RAMP), or DNA replication factor 2 (CDT2), is reported to be correlated with the cell proliferation, cell cycle arrest and cell invasion in hepatocellular carcinoma, breast cancer and gastric cancer. Immune infiltration analysis demonstrated that macrophages MO, macrophages Ml and T cells CD4 memory activated were linked to pathogenesis of NPC. Conclusion: In summary, we adopted a comprehensive strategy to screen DTL as biomarkers related to NPC and explore the critical role of immune cell infiltration in NPC.

关键词： nasopharyngeal carcinoma NPC biomarkers machine learning algorithm DTL

来源：评论

学校读者我要写书评

暂无评论

machine learning in Finance: A Case Study on Forecasting Google's Stock Price

Machine Learning in Finance: A Case Study on Forecasting Goo...

引用

作者： Tianyi Kong Smith School of Business Queen's University

Stock price prediction remains an attractive and essential area in financial markets,with researchers constantly working hard to improve existing models or develop new ones to achieve more accurate predictions. Foreseeing the future direction of stock prices allowing people to plan and formulate effective investment strategies. However, predicting stock prices remains a difficult challenge due to many uncontrollable factors. Traditional forecasting methods rely primarily on economic data analysis and formulation. However,these traditional methods often provide limited information and forecast accuracy due to market uncertainty. Many business organizations and individual investors started to utilize the programmed approaches to improve the accuracy of stock price predictions as machine learning and deep learning capabilities continue to advance. Through an actual case study,this essay examines the innovative use of machine learning methods for researching in the field of predicting stock prices. In the case study, an LSTM model is built to find the transforming trend of the stock price, while Google's stock price is collected to use as the dataset for training the model. The article finally conducts a comparative study on stock price prediction based on LSTM is conducted to clarify its working progress and accuracy of the outcome.

关键词： Stock price prediction machine learning algorithm LSTM

来源：评论

学校读者我要写书评

暂无评论

Comparison of machine learning algorithms in Screening Potential Additives to Ni/Al2O3 Methanation Catalysts for Improving the Anti-Coking Performance

引用

CHEMISTRYSELECT 2019年第40期4卷 11790-11795页

作者： Han, Xiaoxia Yue, Lin Zhao, Chaofan Jiang, Shaohua Liu, Junjie Li, Yuting Ren, Jun Taiyuan Univ Technol Coll Elect & Power Engn 79 Yingze West St Taiyuan 030024 Shanxi Peoples R China Wuyi Univ Sch Biotechnol & Hlth Sci 22 Dongcheng Village Jiangmen 529020 Peoples R China Natl Inst Metrol Div Nanoscale Measurement & Adv Mat 18 Bei San Huan Dong Lu Beijing 100029 Peoples R China Taiyuan Univ Technol Key Lab Coal Sci & Technol 79 Yingze West St Taiyuan 030024 Shanxi Peoples R China

In this paper, the 16 physicochemical properties of 56 elements were processed through principal component analysis (PCA) transformation and Gaussian mixture model clustering. And then, a pool of eleven representative elements was chosen for subsequent experiments on resistance to carbon deposition. Based on the experimental results and the principal components of the selected elements, radial basis function network (RBFN), support vector machine (SVM) and Gaussian process regression (GPR) models were constructed, respectively. Compared with other models, the prediction results of GPR model are more accurate. It predicted that W element is the most effective additive, which was confirmed by further experiments. To our knowledge, this finding has not yet been formally reported in the literature. The application and implementation of this strategy provides new ideas for high dimensional, small sample and nonlinear catalyst data modeling.

关键词： Additives Anti-coking machine learning algorithm Methanation Ni Al2O3 catalyst

来源：评论

学校读者我要写书评

暂无评论

Research on algorithms for control design of human-machine interface system using ML

引用

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2022年第SUPPL 1期13卷 462-469页

作者： Zhang, Xin Beram, Shehab Mohamed Haq, Mohd Anul Wawale, Surindar Gopalrao Buttar, Ahmed Mateen Zibo Vocat Inst Dept Art & Design Zibo 255000 Shandong Peoples R China Sunway Univ Kuala Lumpur Subang Jaya Malaysia Majmaah Univ Coll Comp Sci & Informat Sci Al Majmaah 11952 Saudi Arabia Agasti Arts Commerce & Dadasaheb Rupwate Sci Coll Akole India Univ Agr Faisalabad Comp Sci Dept Faisalabad Pakistan

In recent years, progressive attention has been paid to the research of man-machine interface. In many fields of application software system development, experts have listed man-machine interface as one of the commands for the urgent research and advancement. This article has proposed the improvement to the man-machine interface system control design for the practical value of life, and has presented an approach for algorithms using machine learning. The method used in the paper includes the spatial layout of human-machine interface supported by the design cognition model and the use of machine learning algorithms. Based on Max-Min Ant System, the optimal path of ant construction is obtained, which is the optimal layout scheme. The experimental result in the paper shows that: with the support of the cognitive model, the cabin man-machine interface system control design method based on Genetic algorithm-Ants algorithm is obtained. The layout design principles were summarized by the cognitive model, and the layout optimization objective function was constructed according to each principle, and the problem of solving layout parties and cases was transformed into a combinatorial optimization problem. The form of fitness function, pheromone, and heuristic information for layout optimization was studied, and the algorithm of manual optimization process was implemented based on Genetic algorithm and Ant algorithm, in order to obtain a good optimization performance and time performance as a result. The practical value of the control design of man-machine interface system with the machine learning algorithm is proved.

关键词： Man-machine interface (M-MI) Cognitive model Ant construction machine learning algorithm Max-min ant system (MMAS) Ant colony optimization (ACO) Meta heuristic approach

来源：评论

学校读者我要写书评

暂无评论

Fetal Health Classification Using machine learning on Cardiotocography Data 8

Fetal Health Classification Using Machine Learning on Cardio...

引用

8th International Conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2025

作者： Karmakar, Samit Ray, Sudipta Basak, Shubhayu Chatterjee, Suvrajeet Kundu, Soumik Kumar Institute of Engineering and Management University of Engineering and Management Department of Electronics & Communication Engineering Kolkata India

ISBN: (纸本)9798331520762

This study explores a machine learning approach for detecting and classifying fetal health which is a crucial aspect in ensuring proper care and wellbeing of both fetus and the mother. The conventional diagnosis methods were manually interpreted from cardiotocography data which leads to subjective or erroneous decisions. With the help of machine learning and accessing cardiotocography data (CTG) it provides some crucial advantages for identification of different fetal physiological states (Normal, Suspected and Pathological) by analyzing different fetal heart rate patterns and provide accurate observations. Analyzing various health parameters, including physiological indicators and factors a elaborate dataset has been utilized to train and evaluate supervised machine learning models. KNN, random forest, logistic regression, decision trees, neural network and gradient boosting has been employed to optimize predictive accuracy. The paper encompasses rigorous preprocessing steps, machine learning algorithm performance and evaluation metrics. Results demonstrate the effectiveness in early detection, providing a foundation for proactive healthcare, diagnostic accuracy, improves maternal-fetal outcomes while addressing issues such as data imbalance and interpretability. Future advancement focuses real time analysis, IOT integration which will bridge the gap between clinical implementation and adoption. © 2025 IEEE.

关键词： cardiotocography data machine learning algorithm real-time analysis

来源：评论

学校读者我要写书评

暂无评论

Improving the Accuracy of the Intrusion Detection System in the Detection of DoS attack using Ada boosting and comparison with SVM 2

Improving the Accuracy of the Intrusion Detection System in ...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Rakesh, T. Nagalakshmi, T.J. Dept. of Electronics and Communication Saveetha School of Engineering Chennai India

ISBN: (纸本)9798350305418

The goal of this research is to create a cutting-edge IDS that uses Ada Boosting (Group 2) and then compare it to a Support Vector machine. (Group 1). The research incorporates two algorithms for two IDS groups namely Ada Boosting and SVM. There are 19 samples in each of two groups, for a total of 38 used in the analysis. SPSS was utilised for the statistical analysis. Using G power and a pretest power of 80%, the sample size was determined. The results show that the IDSs work well, with a significance level of p 0.05. Innovative Intrusion Detection System with Ada Boosting dramatically increases IDS accuracy with increasing percentages, and this improvement is statistically significant at the 0.0, or p 0.05 level. The Mean accuracy of Ada Boosting for (Group 2) is 0.994 and with SVM (Group 1) is 0.985. By comparing the performance of the Ada Boosting based IDS and SVM based IDS, Ada boosting based IDS significantly perform better. © 2023 IEEE.

关键词： Accuracy Ada Boosting Innovative Intrusion Detection System KDDCup99 dataset machine learning algorithm Predictive modelling Support Vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Prognostic value, DNA variation and immunologic features of a tertiary lymphoid structure-related chemokine signature in clear cell renal cell carcinoma

引用

CANCER IMMUNOLOGY IMMUNOTHERAPY 2022年第8期71卷 1923-1935页

作者： Xu, Wenhao Ma, Chunguang Liu, Wangrui Anwaier, Aihetaimujiang Tian, Xi Shi, Guohai Qu, Yuanyuan Wei, Shiyin Zhang, Hailiang Ye, Dingwei Fudan Univ Shanghai Canc Ctr Shanghai Med Coll Dept Urol Dongan Rd 270 Shanghai 200032 Peoples R China Youjiang Med Univ Nationalities Affiliated Hosp Zhongshan 2nd Rd 18 Baise 533000 Peoples R China

Background The tumor microenvironment (TME) and tertiary lymphoid structures (TLS) affect the occurrence and development of cancers. How the immune contexture interacts with the phenotype of clear cell renal cell carcinoma (ccRCC) remains unclear. Methods We identified and evaluated TLS clusters in ccRCC using machine learning algorithms and the 12-chemokine gene signature for TLS. Analyses for functional enrichment, DNA variation, immune cell distribution, association with independent clinicopathological features and predictive value of CXCL13 in ccRCC were performed. Results We found a prominently enrichment of the 12-chemokine gene signature for TLS in patients with ccRCC compared with other types of renal cell carcinoma. We identified a prognostic value of CCL4, CCL5, CCL8, CCL19 and CXCL13 expression in ccRCC. DNA deletion of the TLS gene signature significantly predicted poor outcome in ccRCC compared with amplification and wild-type gene signature. We established TLS clusters (C1-4) and observed distinct differences in survival, stem cell-like characteristics, immune cell distribution, response to immunotherapies and VEGF-targeted therapies among the clusters. We found that elevated CXCL13 expression significantly predicted aggressive progression and poor prognosis in 232 patients with ccRCC in a real-world validation cohort. Conclusion This study described a 12-chemokine gene signature for TLS in ccRCC and established TLS clusters that reflected different TME immune status and corresponded to prognosis of ccRCC. We confirmed the dense presence of TILs aggregation and TLS in ccRCC and demonstrated an oncogenic role of CXCL13 expression of ccRCC, which help develop immunotherapies and provide novel insights on the long-term management of ccRCC.

关键词： Clear cell renal cell carcinoma Tertiary lymphoid structures Tumor microenvironment Prognosis CXCL13 machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：